AI & Machine Learning · Computer Science & AI
Computation & Language / NLP
The newest papers in Computation & Language / NLP that ReadSearch has read, newest first. Each links to its own page, with its authors, date, where it was published and the original.
The newest 5,000 papers, from 17 September 2026 to 5 November 2026: 5,000 arXiv preprints.
Get the few papers worth your time in Computation & Language / NLP every morning.
Follow Computation & Language / NLP and ReadSearch reads its new papers each day, then brings you the few worth reading, each with its key finding in a sentence.
Newest papers, page 164
Tracking Is Not Permanence: What Video World Models Keep of a Hidden Object
Video world models track objects they can see; we ask what they keep of objects they cannot.Who Wrote It Is Not Enough: Detecting Who Contributed the Insight
As LLMs increasingly assist scientific writing and peer review, detecting who wrote the text is no longer sufficient: we need to determine who contributed the underlying insight.AccentCL: Robust Accent Classification with Incremental Expansion
Accent classifiers are typically trained with a fixed label inventory and cannot accommodate new accent categories as new data becomes available.AlignQuant: Tile-Aligned Mixed-Precision Quantization for Efficient LLM Generation
Fine-grained mixed-precision quantization promises efficient large language model inference, but local precision choices can conflict with regular GPU storage and computation units.Auditable Claims about AI Agents
Organizations make claims about their AI agents: a person approves every external email, every action is logged, an evaluation shows the agent is safe to deploy.In With the Old: Enhancing 'Classical' Document Automation with Generative AI
Software-based legal assistance systems have leveraged many different forms of knowledge representation and reasoning.Closing Ambient Clinical Documentation Gaps with Automated Provider Queries
Provider queries are clarifying requests sent by clinical documentation specialists to physicians to close gaps in the clinical note and ensure accurate billing.On Open-Ended Information Seeking for Information Elicitation Agents
Information elicitation is an open-ended information-seeking problem in which an interaction can unfold in many potentially valuable directions, requiring an elicitor to continually determine which…Not What a Child Expressed: Auditing the Sign-to-Text Safety Interface in Child-Facing AI
Automatic sign language translation (SLT) has entered consumer products, turning American Sign Language into English text for dictation, messaging, and queries put to a conversational assistant.Safeguarding LLMs via Model-Agnostic Latent Safety Signals from Dark Knowledge
LLMs have advanced rapidly, raising growing concerns about their safety.LRCC: Generalizing Low-Rank Compression with Conditional Computation
Low-rank compression reduces the cost of pretrained language models by replacing linear transformations with low-rank factorizations.Agent Behavior as Code: Efficient and Robust LLM Agents with Programmatic Specifications
AI agents based on foundation models (FMs) have demonstrated strong capabilities to perform complex open-ended tasks.Viva La Vida: Verification and Accumulation Failures in Multi-Agent Proof Search
When an agentic prover works on an open problem, there is no proof assistant to fall back on: its verifier and lemma library are ultimately language models judging model outputs.Cluster Validation Indices as Self-Supervised Objectives for Text Representation Learning
Self-supervised fine-tuning refines the embedding space of a pretrained language encoder without labels.CURIO: Curiosity-Driven Test-Time Learning for Open-Ended Discovery
Open-ended discovery requires learning from repeated attempts while continuing to explore directions whose value is not yet apparent.SpecFold: Folding Multi-Branch Redundancy for Faster Speculative Decoding in Diffusion Language Models
Diffusion large language models (DLLMs) generate text through iterative block denoising, and multi-branch speculative decoding accelerates this process by verifying a main branch together with…No Hindsight for LLM Fact-Checkers: Measuring Leakage Channels in Misinformation Detection
As automated fact-checking scales on social media, large language model (LLM) verdict scores can look stronger than warranted.A Systematic Analysis of the Predictive Power of LM Surprisal in Reading Chinese
This study analyzes the predictive power of LM-derived, token-level surprisal on Mandarin Chinese reading times.Rewrite What Matters: Adaptive Multilingual Query Rewriting for Reasoning via Agentic Reinforcement Learning
In multilingual scenarios, queries with equivalent semantics but in different languages could guide the model into different reasoning trajectories, leading to performance disparities.Scaling Verifiable Environments for Long-horizon Work Agents
Work agents operate over digital artifacts to execute professional knowledge-intensive work, requiring training environments that support long-horizon interaction and trustworthy verification.